R 學習筆記－天天向上

R-intro.pdf為官方手冊,值得初學者研讀

線上中文版: R 導論

宣告一個變數名稱為 x 的向量, 其中 <- 為指派運算子(assign operator)

   1: > x <- c(1, 2, 3, 4, 5)   2: > x   3: [1] 1 2 3 4 5

同理, 另一種等效運算子–>

   1: > c(6, 7, 8, 9, 10)->x   2: > x   3: [1]  6  7  8  9 10

也可以用assign指令,

   1: > assign("x", c(2, 3, 4))   2: > x   3: [1] 2 3 4

堆疊向量: y = [x 0 2*x] ,

   1: > x   2: [1] 2 3 4   3: > y<-c(x, 0, 2*x)   4: > y   5: [1] 2 3 4 0 4 6 8

其中x為3個元素的向量, 因此y的元素個數為7個

   1: > length(x)   2: [1] 3   3: > length(y)   4: [1] 7

最小值min() 最大值max() 平均值mean(), 加總sum(), 乘積prod()

   1: > z = c(min(x), max(x), mean(x), sum(x), prod(x))   2: > z   3: [1]  2  4  3  9 24

plot( z )

   1: > sum((x-mean(x))^2)/(length(x)-1)   2: [1] 2.5   3: > var(x)   4: [1] 2.5

查詢 help

   1: help("sort")   2: tarting httpd help server ... done   3:  sort(x,decreasing =FALSE)   4: 1] 1 2 3 4 5   5:  sort(x,decreasing =TRUE)   6: 1] 5 4 3 2 1

2015/01/10

pg. 1~14 sect. 2.3 Generating regular sequences

產生1,2,~15序列

   1: > s1 = 1:15   2: > s1   3:  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15

下指令seq()也可以

   1: > s2 = seq(from=1, to=15)   2: > s2   3:  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15

產生間隔2的序列

   1: > s3 = seq(from=1, to=15, by=2)   2: > s3   3: [1]  1  3  5  7  9 11 13 15

產生間隔0.5遞減序列

   1: > s4 = seq(from=14, to=1, by = -0.5)   2: > s4   3:  [1] 14.0 13.5 13.0 12.5 12.0 11.5 11.0 10.5 10.0  9.5  9.0  8.5  8.0  7.5   4: [15]  7.0  6.5  6.0  5.5  5.0  4.5  4.0  3.5  3.0  2.5  2.0  1.5  1.0

NA: not available一般用來表示missing value或一些特殊狀況

   1: > 0/0   2: [1] NaN   3: > Inf-Inf   4: [1] NaN

定義一個z序列如下

   1: > z = c(1:3, NA, 3:-1)   2: > z   3: [1]  1  2  3 NA  3  2  1  0 -1   4: > z>0   5: [1]  TRUE  TRUE  TRUE    NA  TRUE  TRUE  TRUE FALSE FALSE

接下來篩選z>0的元素, 其中[]內為篩選條件,第一個>0, 第二個為有限is.finite(), 兩個條件進行&運算後, 當作z的布林篩選條件,

其結果為true的保留下來, 為false剔除

   1: > x = z[ z>0 & is.finite(z)]   2: > x   3: [1] 1 2 3 3 2 1

paste()指令

The paste() function takes an arbitrary number of arguments and concatenates them one by
one into character strings.

   1: > x = paste(c("str1", "str2"), 1:3)   2: > x   3: [1] "str1 1" "str2 2" "str1 3"   4: > x[1]   5: [1] "str1 1"   6: > x[2]   7: [1] "str2 2"   8: > x[3]   9: [1] "str1 3"

2015/1/11 p16 2.6 Character vectors 眨眼睛

產生字串x1,y2,x3,y4,…字母和數字中間沒有”空格”

   1: > x<-paste(c("X","Y"), 1:10, sep="")   2: > x   3:  [1] "X1"  "Y2"  "X3"  "Y4"  "X5"  "Y6"  "X7"  "Y8"  "X9"  "Y10"

若省略sep參數, 字母與數字中間會有空格

   1: > y = paste(c("X","Y"), 1:10)   2: > y   3: [1] "X 1"  "Y 2"  "X 3"  "Y 4"  "X 5"  "Y 6"  "X 7"  "Y 8"  "X 9"  "Y 10"

若字母與數字中間想插入”_”底線

   1: > z<-paste(c("X","Y"), 1:10, sep="_")   2: > z   3:  [1] "X_1"  "Y_2"  "X_3"  "Y_4"  "X_5"  "Y_6"  "X_7"  "Y_8"  "X_9"  "Y_10"

類似MATLAB repmat

語法: rep( array, times = N)

   1: > rep( c(1,2), times=3)   2: [1] 1 2 1 2 1 2

rep( c(1,2,3), times=2) 重複array [1, 2, 3]兩次, 並將其結果當作另一個陣列索引值

   1: > rep(c(1,2,3), times=2)   2: [1] 1 2 3 1 2 3   3: > c(1.1, 1.2, 1.3)[rep(c(1,2,3), times=2)]   4: [1] 1.1 1.2 1.3 1.1 1.2 1.3

-------------------------------------------------------------------------------------------------------------

產生一個序列z = [0,1,2…9], 接著利用as物件進行資料型態轉型, 轉字元as.character()並存成z_str

接著, 將該字元陣列轉回數值陣列 z_num, 並利用z==z_num驗證兩個數值陣列相同

   1: > z = 0:9   2: > z_str = as.character(z)   3: > z_str   4:  [1] "0" "1" "2" "3" "4" "5" "6" "7" "8" "9"   5: > z_num = as.numeric(z_str)   6: > z_num   7:  [1] 0 1 2 3 4 5 6 7 8 9   8: > z==z_num   9:  [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

產生一個變數x, 初始化empty物件(數值類型), 指定第三個元素=5, 其他未定義的元素則為NA

   1: > x <- numeric()   2: > x   3: numeric(0)   4: > x[3] = 5   5: > x   6: [1] NA NA  5

利用is.na()來判定哪些元素為not available

   1: > is.na(x)   2: [1]  TRUE  TRUE FALSE

A ragged array

索引:x = 1 2 3 4 5 1 2 3 4 5 6

數值:val = 1 2 3 4 5 6 7 8 9 10 11

將索引分類

   1: > xf   2:  [1] 1 2 3 4 5 1 2 3 4 5 6   3: Levels: 1 2 3 4 5 6

根據索引分類, 並套用mean(), 計算相同分群間的平均值

其中tapply()為內建函式:Apply a Function Over a Ragged Array

   1: > y<-tapply(1:11, xf, mean)   2: > y   3:    1    2    3    4    5    6    4:  3.5  4.5  5.5  6.5  7.5 11.0 

試試看如果要取相同分群的min, max和sum

   1: > z1<-tapply(val, xf, max)   2: > z2<-tapply(val, xf, min)   3: > z1   4:  1  2  3  4  5  6    5:  6  7  8  9 10 11    6: > z2   7:  1  2  3  4  5  6    8:  1  2  3  4  5 11    9: > z3<-tapply(val, xf, sum)  10: > z3  11:  1  2  3  4  5  6   12:  7  9 11 13 15 11 

自定義function pointer

stderr <- function(x) sqrt(var(x)/length(x))

   1: > stderr <- function(x) sqrt(var(x)/length(x))   2: > z4<-tapply(val, xf, stderr)   3: > z4   4:   1   2   3   4   5   6    5: 2.5 2.5 2.5 2.5 2.5  NA 

呼叫ordered()

   1: > z5<-tapply(val, xf, ordered)   2: > z5   3: $`1`   4: [1] 1 6   5: Levels: 1 < 6   6:     7: $`2`   8: [1] 2 7   9: Levels: 2 < 7  10:    11: $`3`  12: [1] 3 8  13: Levels: 3 < 8  14:    15: $`4`  16: [1] 4 9  17: Levels: 4 < 9  18:    19: $`5`  20: [1] 5  10  21: Levels: 5 < 10  22:    23: $`6`  24: [1] 11  25: Levels: 11